PyNeRF：金字塔形神經輻射場

摘要

神經輻射場（NeRFs）可以通過空間網格表示大幅加速。然而，它們並未明確地考慮尺度，因此在重建以不同攝像機距離捕捉的場景時會引入混疊異構。Mip-NeRF及其擴展提出了具有尺度感知的渲染器，該渲染器投影體積錐體而不是點樣本，但這些方法依賴於位置編碼，這些編碼與網格方法不太相容。我們提出了一種對基於網格的模型進行簡單修改的方法，即在不同的空間網格分辨率下訓練模型頭。在渲染時，我們簡單地使用更粗糙的網格來渲染涵蓋更大體積的樣本。我們的方法可以輕鬆應用於現有的加速NeRF方法，並顯著改善渲染質量（在合成和無邊界的真實場景中將錯誤率降低20-90%），同時產生最小的性能開銷（因為每個模型頭的評估速度很快）。與Mip-NeRF相比，我們將錯誤率降低了20%，同時訓練速度提高了60倍。

English

Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera distances. Mip-NeRF and its extensions propose scale-aware renderers that project volumetric frustums rather than point samples but such approaches rely on positional encodings that are not readily compatible with grid methods. We propose a simple modification to grid-based models by training model heads at different spatial grid resolutions. At render time, we simply use coarser grids to render samples that cover larger volumes. Our method can be easily applied to existing accelerated NeRF methods and significantly improves rendering quality (reducing error rates by 20-90% across synthetic and unbounded real-world scenes) while incurring minimal performance overhead (as each model head is quick to evaluate). Compared to Mip-NeRF, we reduce error rates by 20% while training over 60x faster.

PyNeRF：金字塔形神經輻射場

PyNeRF: Pyramidal Neural Radiance Fields

摘要

Support